Vehicle positioning method, device, computer equipment and storage medium

Abstract

The present application relates to a vehicle positioning method, device, computer equipment, storage medium and computer program product. The method includes: if a QR code is detected by a laser radar, then the laser radar is used to determine the direction vector between the vehicle and each detected QR code; determine the position information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors; based on the position information of the QR code corresponding to each target direction vector and each target direction vector, determine the vehicle position information corresponding to each target direction vector, and determine the actual position information of the vehicle at the current detection moment based on the vehicle position information corresponding to each target direction vector. The laser radar is used to obtain the QR code, and the position information of the QR code is determined by identifying and parsing the QR code. Then, the vehicle position is calculated based on the relatively accurate relative position between the vehicle and the QR code determined by the laser radar.

Description

Technical Field

[0001] The present application relates to the field of vehicle positioning technology, and in particular to a vehicle positioning method, apparatus, computer equipment, and storage medium. Background Art

[0002] In today's society, vehicles have become an indispensable means of transportation. With the advancement of modern science and technology, autonomous vehicles are gradually becoming part of our daily lives. Autonomous vehicles are intelligent vehicles that use onboard sensors to perceive their surroundings. Based on this information, they automatically plan routes and control the vehicle to reach its intended destination.

[0003] Vehicle positioning is an essential technology for autonomous vehicles. Currently, vehicle positioning is accomplished by placing QR codes containing location information on the ground or on the guide rails of personal rapid transit systems. However, QR codes placed on the ground can wear out, which can affect vehicle positioning results. Furthermore, the positioning process directly uses the location information corresponding to the QR code scanned by the vehicle as the vehicle's location. However, it is unlikely that the vehicle will be located exactly where the QR code is located, resulting in inaccurate positioning results. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product that can obtain accurate positioning of a vehicle in response to the above technical problems.

[0005] In a first aspect, the present application provides a vehicle positioning method. The method is applied to a vehicle, wherein the vehicle is equipped with a laser radar, and a QR code is provided on a non-ground portion of the vehicle's lane, the QR code carrying the QR code's location information; the method comprises:

[0006] If a QR code is detected by the LiDAR, then the direction vector between the vehicle and each detected QR code is determined by the LiDAR;

[0007] Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0008] Based on the location information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle location information corresponding to each target direction vector is determined, and based on the vehicle location information corresponding to each target direction vector, the actual location information of the vehicle at the current detection moment is determined.

[0009] In one embodiment, the process of determining the target direction vector includes:

[0010] Get the estimated location information of the vehicle at the current detection time;

[0011] Determine the estimated position information of the QR code corresponding to each direction vector based on the estimated position information of the vehicle at the current detection moment;

[0012] The estimated position information of the QR code corresponding to each direction vector is matched with the position information of the QR code in the QR code information database, and the direction vector with successful matching is used as the target direction vector.

[0013] In one embodiment, the vehicle is provided with a camera; the process of determining the target direction vector includes:

[0014] Take a picture with a camera, intercept the QR code image corresponding to each direction vector in the image taken by the camera, identify each successfully intercepted QR code image, and use the direction vector corresponding to the successfully intercepted and identified QR code image as the target direction vector.

[0015] In one embodiment, the vehicle is provided with a camera; the process of determining the target direction vector includes:

[0016] Taking a picture with a camera, intercepting a QR code image corresponding to each direction vector in the image captured by the camera, recognizing each successfully intercepted QR code image, forming a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forming a second set of direction vectors from all direction vectors after removing the first set, and using all direction vectors in the first set as target direction vectors;

[0017] Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

[0018] In one embodiment, the vehicle is provided with an odometer; obtaining the estimated position information of the vehicle at the current detection time includes:

[0019] Obtain the vehicle's travel distance from the last detection time to the current detection time through the odometer;

[0020] The estimated position information of the vehicle at the current detection time is determined based on the actual position information of the vehicle at the previous detection time, the driving direction and the driving distance of the vehicle at the previous detection time.

[0021] In one embodiment, the QR code carries information about the road orientation of the QR code; after the direction vector corresponding to the successfully captured and recognized QR code image is used as the target direction vector, the method further includes:

[0022] Based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, the QR code corresponding to each target direction vector is converted into a front view through affine transformation to obtain the rotation matrix corresponding to each target direction vector;

[0023] The vehicle's driving direction at the current detection moment is determined based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the QR code image corresponding to each target direction vector.

[0024] In a second aspect, the present application also provides a vehicle positioning device. The device is installed on a vehicle, the vehicle is equipped with a laser radar, and a QR code is set on a non-ground portion of the lane where the vehicle is traveling, and the QR code carries the location information of the QR code; the device includes:

[0025] A first determination module is configured to determine a direction vector between the vehicle and each detected QR code by the laser radar if the QR code is detected by the laser radar;

[0026] A second determination module is used to determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0027] The third determination module is used to determine the vehicle position information corresponding to each target direction vector based on the position information of the QR code corresponding to each target direction vector and each target direction vector, and determine the actual position information of the vehicle at the current detection time based on the vehicle position information corresponding to each target direction vector

[0028] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0029] If a QR code is detected by the LiDAR, then the direction vector between the vehicle and each detected QR code is determined by the LiDAR;

[0030] Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0031] Based on the location information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle location information corresponding to each target direction vector is determined, and based on the vehicle location information corresponding to each target direction vector, the actual location information of the vehicle at the current detection moment is determined.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0033] If a QR code is detected by the LiDAR, then the direction vector between the vehicle and each detected QR code is determined by the LiDAR;

[0034] Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0035] Based on the location information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle location information corresponding to each target direction vector is determined, and based on the vehicle location information corresponding to each target direction vector, the actual location information of the vehicle at the current detection moment is determined.

[0036] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0037] If a QR code is detected by the LiDAR, then the direction vector between the vehicle and each detected QR code is determined by the LiDAR;

[0038] Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0039] Based on the location information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle location information corresponding to each target direction vector is determined, and based on the vehicle location information corresponding to each target direction vector, the actual location information of the vehicle at the current detection moment is determined.

[0040] The above-mentioned vehicle positioning method, apparatus, computer equipment, storage medium, and computer program product, if a QR code is detected by a laser radar, then determines the direction vector between the vehicle and each detected QR code through the laser radar; determines the position information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors; determines the vehicle position information corresponding to each target direction vector based on the position information of the QR code corresponding to each target direction vector and each target direction vector; and determines the actual position information of the vehicle at the current detection moment based on the vehicle position information corresponding to each target direction vector. The laser radar utilizes the different reflectivity characteristics of different metals to obtain the QR code, and obtains the position information of the QR code by identifying and parsing the QR code. Then, combined with the relatively accurate relative position between the vehicle and the QR code determined by the laser radar, a particle filter algorithm is used to calculate the vehicle position. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A diagram showing an application environment of a vehicle positioning method according to an embodiment;

[0042] Figure 2 1 is a flow chart of a vehicle positioning method according to an embodiment;

[0043] Figure 3 A schematic diagram of the deployment of a QR code in one embodiment;

[0044] Figure 4 A schematic diagram of a QR code in another embodiment;

[0045] Figure 5 1 is a flow chart of a vehicle positioning method according to an embodiment;

[0046] Figure 6 1 is a flow chart of a vehicle positioning method according to an embodiment;

[0047] Figure 7 is a flow chart of a vehicle positioning method according to another embodiment;

[0048] Figure 8 1 is a flow chart of a vehicle positioning method according to another embodiment;

[0049] Figure 9 is a structural block diagram of a vehicle positioning device in one embodiment;

[0050] Figure 10 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0052] The vehicle positioning method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network, and specifically transmits the detected QR code image or information to the server 104, and the server 104 processes the detected QR code to obtain the vehicle's location information. The data storage system can store the QR code image or information that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 is a device for obtaining QR code images or information, which can include but is not limited to various personal computers, laptops, smart phones, tablet computers and logistics network equipment with laser radar. The server 104 server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0053] In one embodiment, Figure 2 As shown, a vehicle positioning method is provided. Taking the method applied to a server configured on a vehicle as an example, the vehicle is provided with a laser radar, and a QR code is provided on a non-ground portion of the lane where the vehicle is traveling. The QR code carries the location information of the QR code, including the following steps:

[0054] Step 202 , if a QR code is detected by the laser radar, then the laser radar is used to determine the direction vector between the vehicle and each detected QR code;

[0055] First, the prerequisite for the implementation of the embodiment of the present application is a specific QR code deployment method, see Figure 3 , including deploying QR codes on both sides of roads without medians, with the spacing and height between all QR codes being consistent, for example, 20m apart and 1.5m high; deploying QR codes on both sides of roads with medians and on the medians, with the spacing and height between all QR codes being consistent. Among them, all QR codes have the same specifications, with both sides attached to metal plates, with a blank area in the middle of the QR code, and the blank area is coated with a layer of smooth metal. This area is the characteristic identifier of the QR code, for example, see Figure 4 The QR code is 20cm*20cm in size, with a 5cm*5cm blank area in the middle as a feature marker. It's understandable that the coating in the feature area is to facilitate LiDAR detection of the QR code, so the coating metal needs to be a smooth metal with high reflectivity.

[0056] The QR code carries information related to vehicle positioning, such as the location information of the QR code deployment site and information about the road where the QR code is deployed (road orientation, road curvature, road slope, road speed limit, etc.). These relevant information can be obtained by identifying the QR code. In order to avoid confusion in the subsequent use of these relevant information, all relevant information is expressed with reference to the same coordinate system, such as the common Northeast Celestial Coordinate System (a rectangular coordinate system consisting of a geographic location zero point, i.e., a location with latitude, longitude, and altitude of 0, the z-axis coincides with the ellipsoid normal, upward is positive (celestial direction), y coincides with the minor semi-axis of the ellipsoid (north), and the x-axis coincides with the major semi-axis of the earth's ellipsoid (east)). The position can be represented by a point (x, y, z) in the Northeast Celestial Coordinate System (which can also be regarded as a position vector), and the road orientation can be represented by Euler angles (pitch, roll, yaw) relative to the Northeast Celestial Coordinate System.

[0057] It should be noted that whether the QR code is deployed vertically on the road or at an angle, in the isolation belt or on both sides of the isolation belt; the specific material of the QR code coating; the type of relevant information carried by the QR code, etc., are not specifically limited in this embodiment.

[0058] Specifically, while the vehicle is driving, the LiDAR periodically emits a laser. This laser is then reflected when it encounters the metal coating at the location of the QR code's feature marker. The reflected signal provides information about the direction and distance between the detected QR code and the LiDAR. This information then provides the direction vector from the LiDAR (vehicle) to the QR code at the current detection moment. The moment the LiDAR receives the reflected laser is considered the current detection moment, which will not be further elaborated. Based on this process, the direction vectors between the vehicle and all detected QR codes can be obtained.

[0059] Step 204: determining the location information of the QR code corresponding to each target direction vector, where all target direction vectors are determined from all direction vectors;

[0060] The target direction vector is the direction vector that can be used to determine the relative position between the QR code and the vehicle. It is understood that not all QR codes detected by the LiDAR can accurately determine their location. This is because, in practice, various errors may exist, such as when the QR code is obscured and its location information cannot be recognized, or when the LiDAR malfunctions and the QR code is detected inaccurately.

[0061] Specifically, the estimated position information of the QR code can be obtained, and the estimated position information of each QR code can be matched with the tracking list of the QR code. If a QR code with close position information can be found in the tracking list, the QR code is matched successfully, and the position information of the QR code can be obtained. The direction vectors corresponding to these successfully matched QR codes are the target direction vectors that can be used to calculate the vehicle position information.

[0062] It should be noted that the establishment of the QR code tracking list is to reduce the computational complexity of the QR code matching process, and refers to a list of QR codes that can be successfully tracked in several consecutive detections. It is understandable that the detection frequency of the laser radar is definitely very high. Combined with the deployment of QR codes on actual roads and the speed of vehicles, most of the QR codes detected at the previous detection moment and the current detection moment of the laser radar will definitely be repeated. Therefore, when matching the QR code detected at the current detection moment, you can directly follow the tracking list of the QR code formed at the detection moment for comparison. In this way, you can find the location information of most QR codes in a very short time and determine most of the target direction vectors. In addition, after all the target direction vectors at the current detection moment are determined, the QR code tracking list can be updated based on the location information of the QR code corresponding to the determined target direction vector, including adding the location information of new QR codes and deleting the location information of QR codes that have not been successfully tracked for several consecutive times.

[0063] Step 206, based on the location information of the QR code corresponding to each target direction vector and each target direction vector, determine the vehicle location information corresponding to each target direction vector, and based on the vehicle location information corresponding to each target direction vector, determine the actual location information of the vehicle at the current detection moment.

[0064] The location information of a QR code refers to the coordinates of the location where the QR code is located, which represent the coordinates of the road where the QR code is located. When a vehicle travels to this location, the vehicle's location information can be obtained. To facilitate subsequent calculations, the location coordinates of the location where the QR code is located can be regarded as a vector pointing from the coordinate origin to the location coordinates, and this vector is stored in the QR code as the location information of the QR code. In other words, the vehicle's location information can be calculated using the location information of the QR code and the relative position vector (direction vector) between the QR code and the vehicle.

[0065] Specifically, the position of a vehicle can be calculated through each target direction vector, and then the vehicle positions obtained through each target direction vector are averaged to determine the actual position information of the vehicle. The actual position information P of the vehicle at the current detection moment t The calculation formula is as follows:

[0066]

[0067] Where n represents the number of target direction vectors; X n is the location information of the QR code corresponding to each target direction vector; T n is the direction vector of each target; f n is the error of the laser radar, that is, the error of the target direction vector, f n The distance s from the laser radar to the QR code n Positive correlation, the specific direction and size are related to the parameters of the lidar itself.

[0068] The vehicle positioning method provided in this embodiment, if a QR code is detected by a laser radar, then the laser radar is used to determine the direction vector between the vehicle and each detected QR code; the position information of the QR code corresponding to each target direction vector is determined, and all target direction vectors are determined from all direction vectors; based on the position information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle position information corresponding to each target direction vector is determined; based on the vehicle position information corresponding to each target direction vector, the actual position information of the vehicle at the current detection moment is determined. In this embodiment, a highly accurate laser radar is used to detect the QR code, and the actual position of the vehicle is determined based on the position information of multiple QR codes detected by the radar and the relative position between the vehicle and each QR code. While obtaining a more accurate vehicle position, it will not cause wear and tear to the QR code.

[0069] In combination with the contents of the above embodiments, in one embodiment, see Figure 5 , the process of determining the target direction vector includes:

[0070] Step 502, obtaining the estimated position information of the vehicle at the current detection time;

[0071] The vehicle's estimated position at the current detection moment is predicted based on the vehicle's actual position at the previous detection moment. At vehicle startup, during the initial LiDAR detection, the vehicle's actual position is calculated by identifying the QR code detected by the LiDAR and then calculating its position. The Kalman filter algorithm then iterates through several detection cycles to determine an initial vehicle position. This serves as the vehicle's actual position at the first detection moment and serves as the basis for calculating the vehicle's estimated position at the second detection moment.

[0072] Step 504: Determine the estimated position information of the QR code corresponding to each direction vector based on the estimated position information of the vehicle at the current detection moment;

[0073] From the definition of the direction vector, we know that if the direction vector is known, the position of the QR code and the position of the vehicle can be determined. Therefore, if the position of the QR code is uncertain, the position of the QR code can be estimated by the estimated position of the vehicle and the direction vector. t Represents the estimated position information of the vehicle at the current detection moment, T n Represents the direction vector corresponding to the QR code, then the estimated position information X′ of the QR code n The calculation formula can be as follows:

[0074] X′ n =P′ t +T n

[0075] Step 506: Match the estimated position information of the QR code corresponding to each direction vector with the position information of the QR code in the QR code information database, and use the successfully matched direction vector as the target direction vector.

[0076] Among them, the QR code information database refers to a database that stores all QR codes and all the information they carry. Therefore, it is not difficult to understand that the estimated position information of the QR code can be matched with the position information of each QR code in the QR code information database. The successfully matched target direction vector can also determine the position information of the QR code corresponding to the target direction vector. Specifically, when matching the estimated position information of the QR code with the position information of each QR code in the QR code information database, the difference between the estimated position information of the QR code and the position information of each QR code is calculated. For example, the estimated position information of the QR code is (x0, y0, z0), and the position information of the first QR code is (x1, y1, z1). The specific formula is as follows:

[0077]

[0078] The position information of the QR code with the smallest difference from the estimated position information of the QR code is selected. If the difference value is within a preset range, it means that the QR code has found the corresponding position information, and the direction vector corresponding to the QR code is used as the target direction vector.

[0079] The vehicle positioning method provided in this embodiment includes the following steps: obtaining the vehicle's estimated position at the current detection moment; determining the QR code's estimated position corresponding to each direction vector based on the vehicle's estimated position at the current detection moment; matching the QR code's estimated position corresponding to each direction vector with the QR code's position information in a QR code database, and using the successfully matched direction vector as the target direction vector. The QR code is acquired by utilizing the varying reflectivity of different metals using a laser radar. The QR code's position information is then obtained by identifying and parsing the QR code. Combined with the relatively accurate relative position between the vehicle and the QR code determined by the laser radar, the vehicle's position is then calculated using a particle filter algorithm.

[0080] In combination with the above embodiments, in one embodiment, the vehicle is provided with a camera; the process of determining the target direction vector includes:

[0081] Take a picture with a camera, intercept the QR code image corresponding to each direction vector in the image taken by the camera, identify each successfully intercepted QR code image, and use the direction vector corresponding to the successfully intercepted and identified QR code image as the target direction vector.

[0082] Among them, when the laser radar detects the QR code, the camera can be triggered to take pictures of all QR codes, and the obtained picture will be used as the QR code picture at the current detection moment; and recognizing the QR code image means obtaining all the information carried by the QR code.

[0083] It should be noted that, based on the direction vector of the QR code and the camera's own shooting parameter information, the position of the QR code corresponding to the direction vector is projected into the photo, and the corresponding QR code image is cropped to obtain the QR code image. In addition, in general, the camera and lidar can be installed in the same position on the vehicle, so that there is no relative distance between the two, or the relative distance is small and negligible. When using the direction vector of the QR code for projection, the error is small and can be projected directly. However, when the camera and lidar are installed at a certain distance, it is necessary to refer to the relative position vector between the camera and lidar to project the position of the QR code. Considering the range of the lidar and the shooting range of the camera, not all QR codes detected by the lidar can find corresponding QR code images in the picture taken by the camera. Therefore, only the direction vector that can find the corresponding QR code image and can be successfully identified is needed as the target direction vector.

[0084] The vehicle positioning method provided in this embodiment uses a camera to capture a QR code image corresponding to each direction vector in the captured image. Each successfully captured QR code image is recognized, and the direction vector corresponding to the successfully captured and recognized QR code image is used as the target direction vector. The QR code is captured by utilizing the varying reflectivity of different metals using a laser radar. The QR code is then recognized and parsed to obtain its location information. Combined with the relatively accurate relative position between the vehicle and the QR code determined by the laser radar, a particle filter algorithm is used to calculate the vehicle's position.

[0085] In combination with the above embodiments, in one embodiment, the vehicle is provided with a camera; the process of determining the target direction vector includes:

[0086] Taking a picture with a camera, intercepting a QR code image corresponding to each direction vector in the image captured by the camera, recognizing each successfully intercepted QR code image, forming a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forming a second set of direction vectors from all direction vectors after removing the first set, and using all direction vectors in the first set as target direction vectors;

[0087] Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

[0088] It should be noted that in this embodiment, the laser radar's ranging range is greater than the effective range of the camera's QR code recognition. Therefore, not all QR codes detected by the laser radar will be recognized by the camera. The direction vectors corresponding to all QR codes detected by the laser radar form a total set, with a total number of direction vectors m. If the number of target direction vectors in the first set is n, the number of direction vectors in the second set is mn.

[0089] This embodiment combines practical application scenarios to provide a more accurate method for determining the target direction vector. First, the purpose of determining the target direction vector is to obtain accurate QR code location information for example, and then calculate the actual location information of the vehicle. It is easy to understand that the more target direction vectors are determined, the more QR code location information can be used in the calculation. Combining the two methods of identifying the QR code image and matching with the QR code information database can screen out more target direction vectors.

[0090] Specifically, see Figure 6 If the laser radar scans the feature mark, the direction vector T from the vehicle to the QR code is obtained n ; Use the camera to take a photo, according to the direction vector T of the QR code n , projecting the QR code's location onto the photo and cropping the corresponding QR code image. The three corner boxes of the QR code in the cropped image are then identified to obtain the QR code's location information. If an image does not contain a corresponding QR code or the QR code cannot be recognized, the estimated QR code location is used to determine whether the code is in the tracking list. If it is, the QR code exists, and the QR code's location information is obtained. If no corresponding QR code image is found and no match is found in the tracking list, it indicates that the LiDAR has some fault or clutter. The signal is ignored, the corresponding direction vector is no longer used, and the laser scan continues.

[0091] It should be noted that due to other traffic participants and obstacles on the road, the QR code recognized by the camera may be blocked, resulting in unrecognizable. If the camera wants to clearly recognize the QR code, it needs to be at a closer distance. Simply using the camera for recognition will result in a smaller number of QR codes being recognized, less information available for calculation, and poor positioning accuracy and robustness. The ranging distance of the lidar is longer, and a larger number of QR codes can be matched to obtain information. The QR code information obtained through tracking and matching is more accurate, and the vehicle position calculated from this is more accurate, so a QR code tracking list is established.

[0092] The vehicle positioning method provided in this embodiment takes a picture with a camera, intercepts the QR code image corresponding to each direction vector in the image captured by the camera, recognizes each successfully intercepted QR code image, forms a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forms a second set of direction vectors from all direction vectors after removing the first set. The direction vectors in the first set are all used as target direction vectors; obtains the estimated position information of the vehicle at the current detection time, determines the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection time, matches the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and uses the direction vectors in the second set that are successfully matched as the target direction vector. The method utilizes the different reflectivity characteristics of laser radar for different metals to obtain the QR code, and obtains the position information of the QR code by recognizing and parsing the QR code, which can better reduce the impact of errors and improve the accuracy and robustness of positioning.

[0093] In conjunction with the contents of the above embodiments, see Figure 7The vehicle is equipped with an odometer; the estimated position information of the vehicle at the current detection time is obtained, including:

[0094] Step 702: Obtain the distance traveled by the vehicle from the last detection time to the current detection time through the odometer;

[0095] The distance traveled by the vehicle is determined by the difference between the odometer reading at the previous detection time and the reading at the current detection time. In other embodiments, the distance traveled by the vehicle from the previous detection time to the current detection time can also be obtained by other acceleration or mileage sensors.

[0096] Step 704 : Determine the estimated position information of the vehicle at the current detection time based on the actual position information of the vehicle at the previous detection time, the driving direction and the driving distance of the vehicle at the previous detection time.

[0097] The vehicle's actual location and direction at the previous detection time are known at the current detection time. Since the time between the two detection times is short, the vehicle's route can be ideally considered a straight line. Therefore, the vehicle's estimated location at the current detection time can be calculated using the following formula:

[0098] P′ t =P t-1 +S t ·H t-1

[0099] Among them, S t H is the distance traveled by the vehicle from the last detection moment to the current detection moment, t-1 is the vehicle's driving direction at the last detection moment.

[0100] In the method provided in the embodiments of this application, the odometer is used to obtain the distance traveled by the vehicle from the last detection time to the current detection time. The vehicle's estimated position information at the current detection time is determined based on the vehicle's actual position information at the last detection time, the vehicle's driving direction at the last detection time, and the distance traveled. The relative position relationship between the vehicle and the QR code, as reflected by the direction vector, is used to determine the estimated position information of the QR code, and then the accurate target direction vector is determined, thereby improving the accuracy and robustness of positioning.

[0101] In combination with the content of the above embodiment, in one embodiment, the QR code carries the road direction information of the QR code; see Figure 8 , after taking the direction vector corresponding to the successfully intercepted and recognized QR code image as the target direction vector, it also includes:

[0102] Step 802: Based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, the QR code corresponding to each target direction vector is converted into a front view through affine transformation to obtain a rotation matrix corresponding to each target direction vector.

[0103] Among them, affine transformation, also known as affine mapping, refers to a linear transformation of a vector space followed by a translation in geometry, transforming it into another vector space. Affine transformation is a linear transformation between two-dimensional coordinates to two-dimensional coordinates. It maintains the "straightness" of two-dimensional graphics (a straight line remains a straight line after transformation) and "parallelism" (the relative position relationship between two-dimensional graphics remains unchanged, parallel lines remain parallel lines, and the position order of points on the straight line remains unchanged). Any affine transformation can be expressed as multiplying a matrix (linear transformation) and adding a vector (translation). The rotation matrix can represent the transformation between two coordinate systems.

[0104] In this embodiment, the QR code image captured by the camera is a picture in a coordinate system with the camera (vehicle) as the origin. In most cases, it is an irregular quadrilateral. The QR code deployed on the road is a front view (of known size) in a coordinate system with the QR code as the coordinate origin. Therefore, the relative position change between the two coordinate systems (that is, between the vehicle and the road where the QR code is located) can be reflected by the rotation matrix between the QR code image and the front view of the QR code.

[0105] Generally, in three-dimensional space, the relative position change between two coordinate systems is expressed by Euler angles, and the rotation matrix Calculating Euler angles The process is as follows:

[0106] θ x =atan2(r 32 ,r 33 )

[0107]

[0108] θ z =atan2(r 21 ,r 11 )

[0109] Step 804 : Determine the driving direction of the vehicle at the current detection moment based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the QR code image corresponding to each target direction vector.

[0110] It is understandable that, when the road orientation and the relative orientation between the road and the vehicle are known, the orientation of the vehicle in the basic coordinate system (the coordinate system that determines the location information of all QR codes and the road orientation) can be easily obtained, specifically:

[0111]

[0112] Among them, n represents the number of target direction vectors, A i is the road orientation of the QR code corresponding to each target direction vector; θ i is the Euler angle corresponding to each target direction vector; Δ i is the angular error of the LiDAR, which is positively correlated with the angular resolution of the LiDAR.

[0113] In the method provided in the embodiments of the present application, based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, and by converting the QR code corresponding to each target direction vector into an orthographic view through an affine transformation, the rotation matrix corresponding to each target direction vector is obtained. Based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the QR code image corresponding to each target direction vector, the vehicle's direction of travel at the current detection moment is determined. The vehicle's direction of travel is obtained through the relative relationship between the vehicle and the QR code, assisting in obtaining more accurate vehicle position information.

[0114] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0115] Based on the same inventive concept, embodiments of the present application further provide a vehicle positioning device for implementing the aforementioned vehicle positioning method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more vehicle positioning device embodiments provided below can be found in the above-described limitations of the vehicle positioning method and will not be further elaborated here.

[0116] In one embodiment, Figure 9As shown, a vehicle positioning device is provided. The device is installed on a vehicle. The vehicle is equipped with a laser radar. A QR code is set on the non-ground part of the lane where the vehicle is traveling. The QR code carries the location information of the QR code. The device includes:

[0117] A first determination module 901 is configured to determine a direction vector between the vehicle and each detected QR code by the laser radar if a QR code is detected by the laser radar;

[0118] A second determining module 902 is configured to determine the location information of the QR code corresponding to each target direction vector, where all target direction vectors are determined from all direction vectors;

[0119] The third determination module 903 is used to determine the vehicle position information corresponding to each target direction vector based on the position information of the QR code corresponding to each target direction vector and each target direction vector, and determine the actual position information of the vehicle at the current detection moment based on the vehicle position information corresponding to each target direction vector.

[0120] In one embodiment, the second determining module 902 is further configured to:

[0121] Get the estimated location information of the vehicle at the current detection time;

[0122] Determine the estimated position information of the QR code corresponding to each direction vector based on the estimated position information of the vehicle at the current detection moment;

[0123] The estimated position information of the QR code corresponding to each direction vector is matched with the position information of the QR code in the QR code information database, and the direction vector with successful matching is used as the target direction vector.

[0124] In one embodiment, the second determining module 902 is further configured to:

[0125] Take a picture with a camera, intercept the QR code image corresponding to each direction vector in the image taken by the camera, identify each successfully intercepted QR code image, and use the direction vector corresponding to the successfully intercepted and identified QR code image as the target direction vector.

[0126] In one embodiment, the second determining module 902 is further configured to:

[0127] Taking a picture with a camera, intercepting a QR code image corresponding to each direction vector in the image captured by the camera, recognizing each successfully intercepted QR code image, forming a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forming a second set of direction vectors from all direction vectors after removing the first set, and using all direction vectors in the first set as target direction vectors;

[0128] Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

[0129] In one embodiment, the second determining module 902 is further configured to:

[0130] Obtain the vehicle's travel distance from the last detection time to the current detection time through the odometer;

[0131] The estimated position information of the vehicle at the current detection time is determined based on the actual position information of the vehicle at the previous detection time, the driving direction and the driving distance of the vehicle at the previous detection time.

[0132] In one embodiment, the vehicle positioning device further includes a fourth determining module configured to:

[0133] Based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, the QR code corresponding to each target direction vector is converted into a front view through affine transformation to obtain the rotation matrix corresponding to each target direction vector;

[0134] The vehicle's driving direction at the current detection moment is determined based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the QR code image corresponding to each target direction vector.

[0135] Each module in the aforementioned vehicle positioning device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0136] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 10As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store all road-related information carried by the QR code. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a vehicle positioning method is implemented.

[0137] Those skilled in the art will understand that Figure 10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0138] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0139] The method is applied to a vehicle, wherein the vehicle is provided with a laser radar, and a QR code is provided on a non-ground portion of a lane in which the vehicle is traveling, the QR code carrying information of the location of the QR code; the method comprises:

[0140] If a QR code is detected by the LiDAR, then the direction vector between the vehicle and each detected QR code is determined by the LiDAR;

[0141] Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0142] Based on the location information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle location information corresponding to each target direction vector is determined, and based on the vehicle location information corresponding to each target direction vector, the actual location information of the vehicle at the current detection moment is determined.

[0143] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0144] Get the estimated location information of the vehicle at the current detection time;

[0145] Determine the estimated position information of the QR code corresponding to each direction vector based on the estimated position information of the vehicle at the current detection moment;

[0146] The estimated position information of the QR code corresponding to each direction vector is matched with the position information of the QR code in the QR code information database, and the direction vector with successful matching is used as the target direction vector.

[0147] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0148] Take a picture with a camera, intercept the QR code image corresponding to each direction vector in the image taken by the camera, identify each successfully intercepted QR code image, and use the direction vector corresponding to the successfully intercepted and identified QR code image as the target direction vector.

[0149] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0150] Taking a picture with a camera, intercepting a QR code image corresponding to each direction vector in the image captured by the camera, recognizing each successfully intercepted QR code image, forming a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forming a second set of direction vectors from all direction vectors after removing the first set, and using all direction vectors in the first set as target direction vectors;

[0151] Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

[0152] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0153] Obtain the vehicle's travel distance from the last detection time to the current detection time through the odometer;

[0154] The estimated position information of the vehicle at the current detection time is determined based on the actual position information of the vehicle at the previous detection time, the driving direction and the driving distance of the vehicle at the previous detection time.

[0155] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0156] Based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, the QR code corresponding to each target direction vector is converted into a front view through affine transformation to obtain the rotation matrix corresponding to each target direction vector;

[0157] The vehicle's driving direction at the current detection moment is determined based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the QR code image corresponding to each target direction vector.

[0158] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0159] If a QR code is detected by the LiDAR, then the direction vector between the vehicle and each detected QR code is determined by the LiDAR;

[0160] Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0161] Based on the location information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle location information corresponding to each target direction vector is determined, and based on the vehicle location information corresponding to each target direction vector, the actual location information of the vehicle at the current detection moment is determined.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0163] Get the estimated location information of the vehicle at the current detection time;

[0164] Determine the estimated position information of the QR code corresponding to each direction vector based on the estimated position information of the vehicle at the current detection moment;

[0165] The estimated position information of the QR code corresponding to each direction vector is matched with the position information of the QR code in the QR code information database, and the direction vector with successful matching is used as the target direction vector.

[0166] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0167] Take a picture with a camera, intercept the QR code image corresponding to each direction vector in the image taken by the camera, identify each successfully intercepted QR code image, and use the direction vector corresponding to the successfully intercepted and identified QR code image as the target direction vector.

[0168] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0169] Taking a picture with a camera, intercepting a QR code image corresponding to each direction vector in the image captured by the camera, recognizing each successfully intercepted QR code image, forming a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forming a second set of direction vectors from all direction vectors after removing the first set, and using all direction vectors in the first set as target direction vectors;

[0170] Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

[0171] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0172] Obtain the vehicle's travel distance from the last detection time to the current detection time through the odometer;

[0173] The estimated position information of the vehicle at the current detection time is determined based on the actual position information of the vehicle at the previous detection time, the driving direction and the driving distance of the vehicle at the previous detection time.

[0174] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0175] Based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, the QR code corresponding to each target direction vector is converted into a front view through affine transformation to obtain the rotation matrix corresponding to each target direction vector;

[0176] The vehicle's driving direction at the current detection moment is determined based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the QR code image corresponding to each target direction vector.

[0177] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0178] If a QR code is detected by the LiDAR, then the direction vector between the vehicle and each detected QR code is determined by the LiDAR;

[0179] Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors;

[0180] Based on the location information of the QR code corresponding to each target direction vector and each target direction vector, the vehicle location information corresponding to each target direction vector is determined, and based on the vehicle location information corresponding to each target direction vector, the actual location information of the vehicle at the current detection moment is determined.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0182] Get the estimated location information of the vehicle at the current detection time;

[0183] Determine the estimated position information of the QR code corresponding to each direction vector based on the estimated position information of the vehicle at the current detection moment;

[0184] The estimated position information of the QR code corresponding to each direction vector is matched with the position information of the QR code in the QR code information database, and the direction vector with successful matching is used as the target direction vector.

[0185] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0186] Take a picture with a camera, intercept the QR code image corresponding to each direction vector in the image taken by the camera, identify each successfully intercepted QR code image, and use the direction vector corresponding to the successfully intercepted and identified QR code image as the target direction vector.

[0187] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0188] Taking a picture with a camera, intercepting a QR code image corresponding to each direction vector in the image captured by the camera, recognizing each successfully intercepted QR code image, forming a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forming a second set of direction vectors from all direction vectors after removing the first set, and using all direction vectors in the first set as target direction vectors;

[0189] Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0191] Obtain the vehicle's travel distance from the last detection time to the current detection time through the odometer;

[0192] The estimated position information of the vehicle at the current detection time is determined based on the actual position information of the vehicle at the previous detection time, the driving direction and the driving distance of the vehicle at the previous detection time.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0194] Based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, the QR code corresponding to each target direction vector is converted into a front view through affine transformation to obtain the rotation matrix corresponding to each target direction vector;

[0195] The vehicle's driving direction at the current detection moment is determined based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the QR code image corresponding to each target direction vector.

[0196] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0197] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0198] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A vehicle positioning method, characterized in that: The method is applied to a vehicle, wherein the vehicle is provided with a laser radar, and a QR code is provided on a non-ground portion of a lane in which the vehicle is traveling, wherein the QR code carries information about the location of the QR code; the method comprises: If a QR code is detected by the laser radar, determining a direction vector between the vehicle and each detected QR code by the laser radar; Determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors; Determining the vehicle position information corresponding to each target direction vector based on the position information of the QR code corresponding to each target direction vector and each target direction vector, and determining the actual position information of the vehicle at the current detection moment based on the vehicle position information corresponding to each target direction vector; The vehicle is provided with a camera; the process of determining the target direction vector includes: Taking a picture with the camera, intercepting a QR code image corresponding to each direction vector in the image captured by the camera, recognizing each successfully intercepted QR code image, forming a first set of direction vectors corresponding to the successfully intercepted and recognized QR code images, and forming a second set of direction vectors remaining after removing the first set from all direction vectors, and using all direction vectors in the first set as target direction vectors; Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

2. The method according to claim 1, characterized in that The process of determining the target direction vector includes: Obtaining estimated position information of the vehicle at the current detection moment; Determining the estimated position information of the QR code corresponding to each direction vector based on the estimated position information of the vehicle at the current detection moment; The estimated position information of the QR code corresponding to each direction vector is matched with the position information of the QR code in the QR code information database, and the direction vector with successful matching is used as the target direction vector.

3. The method according to claim 1, characterized in that The vehicle is provided with a camera; The process of determining the target direction vector includes: Take a picture with the camera, intercept the QR code image corresponding to each direction vector in the image taken by the camera, identify each successfully intercepted QR code image, and use the direction vector corresponding to the successfully intercepted and identified QR code image as the target direction vector.

4. The method according to claim 1 or 2, characterized in that The vehicle is provided with an odometer; and obtaining the estimated position information of the vehicle at the current detection time includes: Obtaining the travel distance of the vehicle from the last detection time to the current detection time through the odometer; The estimated position information of the vehicle at the current detection time is determined based on the actual position information of the vehicle at the last detection time, the driving direction of the vehicle at the last detection time, and the driving distance.

5. The method according to claim 3, characterized in that The QR code carries information about the road orientation of the QR code; after the direction vector corresponding to the successfully intercepted and recognized QR code image is used as the target direction vector, the method further includes: Based on the positions of the three corner boxes in the QR code image corresponding to each target direction vector, the QR code corresponding to each target direction vector is converted into a front view through affine transformation to obtain the rotation matrix corresponding to each target direction vector; The driving direction of the vehicle at the current detection moment is determined based on the rotation matrix corresponding to each target direction vector and the road orientation information carried in the two-dimensional code image corresponding to each target direction vector.

6. A vehicle positioning device, characterized in that: The device is installed on a vehicle, the vehicle is provided with a laser radar, and a QR code is provided on a non-ground portion of the lane where the vehicle is traveling, the QR code carrying the location information of the QR code; the device includes: a first determining module, configured to determine, by the laser radar, a direction vector between the vehicle and each detected QR code if a QR code is detected by the laser radar; A second determination module is used to determine the location information of the QR code corresponding to each target direction vector, and all target direction vectors are determined from all direction vectors; a third determination module, configured to determine the vehicle position information corresponding to each target direction vector based on the position information of the QR code corresponding to each target direction vector and each target direction vector, and determine the actual position information of the vehicle at the current detection moment based on the vehicle position information corresponding to each target direction vector; The second determination module is further configured to take a picture using a camera, intercept a QR code image corresponding to each direction vector in the image captured by the camera, identify each successfully intercepted QR code image, form a first set of direction vectors corresponding to the successfully intercepted and identified QR code images, and form a second set of direction vectors remaining after removing the first set from all direction vectors, and use all direction vectors in the first set as target direction vectors; Obtain the estimated position information of the vehicle at the current detection moment, determine the estimated position information of the QR code corresponding to each direction vector in the second set based on the estimated position information of the vehicle at the current detection moment, match the estimated position information of the QR code corresponding to each direction vector in the second set with the position information of the QR code in the QR code information database, and use the successfully matched direction vector in the second set as the target direction vector.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images